FFmpeg
h264dsp_init_arm.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2010 Mans Rullgard <mans@mansr.com>
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 #include <stdint.h>
22 
23 #include "libavutil/attributes.h"
24 #include "libavutil/arm/cpu.h"
25 #include "libavcodec/h264dsp.h"
27 
28 void ff_h264_v_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
29  int beta, int8_t *tc0);
30 void ff_h264_h_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
31  int beta, int8_t *tc0);
32 void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
33  int beta, int8_t *tc0);
34 void ff_h264_h_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
35  int beta, int8_t *tc0);
37  int beta, int8_t *tc0);
38 
40  int log2_den, int weight, int offset);
42  int log2_den, int weight, int offset);
44  int log2_den, int weight, int offset);
45 
47  int height, int log2_den, int weightd,
48  int weights, int offset);
50  int height, int log2_den, int weightd,
51  int weights, int offset);
53  int height, int log2_den, int weightd,
54  int weights, int offset);
55 
56 void ff_h264_idct_add_neon(uint8_t *dst, int16_t *block, int stride);
57 void ff_h264_idct_dc_add_neon(uint8_t *dst, int16_t *block, int stride);
58 void ff_h264_idct_add16_neon(uint8_t *dst, const int *block_offset,
59  int16_t *block, int stride,
60  const uint8_t nnzc[6*8]);
61 void ff_h264_idct_add16intra_neon(uint8_t *dst, const int *block_offset,
62  int16_t *block, int stride,
63  const uint8_t nnzc[6*8]);
64 void ff_h264_idct_add8_neon(uint8_t **dest, const int *block_offset,
65  int16_t *block, int stride,
66  const uint8_t nnzc[6*8]);
67 
68 void ff_h264_idct8_add_neon(uint8_t *dst, int16_t *block, int stride);
69 void ff_h264_idct8_dc_add_neon(uint8_t *dst, int16_t *block, int stride);
70 void ff_h264_idct8_add4_neon(uint8_t *dst, const int *block_offset,
71  int16_t *block, int stride,
72  const uint8_t nnzc[6*8]);
73 
75  const int chroma_format_idc)
76 {
77 #if HAVE_NEON
78  if (bit_depth == 8) {
82 
83  if (chroma_format_idc <= 1)
85  else
87 
91 
95 
100  if (chroma_format_idc <= 1)
105  }
106 #endif // HAVE_NEON
107 }
108 
110  const int chroma_format_idc)
111 {
112  int cpu_flags = av_get_cpu_flags();
113 
114 #if HAVE_ARMV6
115  if (have_setend(cpu_flags))
117 #endif
118  if (have_neon(cpu_flags))
119  h264dsp_init_neon(c, bit_depth, chroma_format_idc);
120 }
#define have_setend(flags)
Definition: cpu.h:31
void ff_h264_h_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
void ff_h264_idct_add16intra_neon(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[6 *8])
void ff_h264_h_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
static atomic_int cpu_flags
Definition: cpu.c:50
#define src
Definition: vp8dsp.c:254
void ff_h264_v_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
H.264 DSP functions.
Macro definitions for various function/variable attributes.
void ff_h264_idct_dc_add_neon(uint8_t *dst, int16_t *block, int stride)
av_cold void ff_h264dsp_init_arm(H264DSPContext *c, const int bit_depth, const int chroma_format_idc)
The exact code depends on how similar the blocks are and how related they are to the block
uint8_t
#define av_cold
Definition: attributes.h:82
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf offset
Undefined Behavior In the C some operations are like signed integer dereferencing freed accessing outside allocated Undefined Behavior must not occur in a C it is not safe even if the output of undefined operations is unused The unsafety may seem nit picking but Optimizing compilers have in fact optimized code on the assumption that no undefined Behavior occurs Optimizing code based on wrong assumptions can and has in some cases lead to effects beyond the output of computations The signed integer overflow problem in speed critical code Code which is highly optimized and works with signed integers sometimes has the problem that often the output of the computation does not c
Definition: undefined.txt:32
h264_weight_func weight_h264_pixels_tab[4]
Definition: h264dsp.h:44
void(* h264_idct_add16intra)(uint8_t *dst, const int *blockoffset, int16_t *block, int stride, const uint8_t nnzc[15 *8])
Definition: h264dsp.h:99
void ff_biweight_h264_pixels_16_neon(uint8_t *dst, uint8_t *src, int stride, int height, int log2_den, int weightd, int weights, int offset)
#define height
void(* h264_idct_add)(uint8_t *dst, int16_t *block, int stride)
Definition: h264dsp.h:81
void ff_weight_h264_pixels_4_neon(uint8_t *dst, int stride, int height, int log2_den, int weight, int offset)
void ff_biweight_h264_pixels_8_neon(uint8_t *dst, uint8_t *src, int stride, int height, int log2_den, int weightd, int weights, int offset)
int(* startcode_find_candidate)(const uint8_t *buf, int size)
Search buf from the start for up to size bytes.
Definition: h264dsp.h:117
void(* h264_idct8_dc_add)(uint8_t *dst, int16_t *block, int stride)
Definition: h264dsp.h:87
void(* h264_h_loop_filter_luma)(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
Definition: h264dsp.h:50
void ff_h264_idct8_add4_neon(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[6 *8])
int ff_startcode_find_candidate_armv6(const uint8_t *buf, int size)
void(* h264_h_loop_filter_chroma)(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
Definition: h264dsp.h:63
void ff_h264_idct8_add_neon(uint8_t *dst, int16_t *block, int stride)
void(* h264_idct_add16)(uint8_t *dst, const int *blockoffset, int16_t *block, int stride, const uint8_t nnzc[15 *8])
Definition: h264dsp.h:90
h264_biweight_func biweight_h264_pixels_tab[4]
Definition: h264dsp.h:45
Context for storing H.264 DSP functions.
Definition: h264dsp.h:42
#define have_neon(flags)
Definition: cpu.h:26
static void bit_depth(AudioStatsContext *s, uint64_t mask, uint64_t imask, AVRational *depth)
Definition: af_astats.c:226
void ff_weight_h264_pixels_16_neon(uint8_t *dst, int stride, int height, int log2_den, int weight, int offset)
void ff_h264_h_loop_filter_chroma422_neon(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
void(* h264_v_loop_filter_luma)(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
Definition: h264dsp.h:48
void ff_h264_idct_add8_neon(uint8_t **dest, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[6 *8])
void(* h264_idct8_add)(uint8_t *dst, int16_t *block, int stride)
Definition: h264dsp.h:83
static av_cold void h264dsp_init_neon(H264DSPContext *c, const int bit_depth, const int chroma_format_idc)
void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
static const int16_t alpha[]
Definition: ilbcdata.h:55
void(* h264_idct8_add4)(uint8_t *dst, const int *blockoffset, int16_t *block, int stride, const uint8_t nnzc[15 *8])
Definition: h264dsp.h:93
void ff_h264_idct8_dc_add_neon(uint8_t *dst, int16_t *block, int stride)
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:93
static int weight(int i, int blen, int offset)
Definition: diracdec.c:1564
void ff_h264_idct_add_neon(uint8_t *dst, int16_t *block, int stride)
void ff_biweight_h264_pixels_4_neon(uint8_t *dst, uint8_t *src, int stride, int height, int log2_den, int weightd, int weights, int offset)
GLint GLenum GLboolean GLsizei stride
Definition: opengl_enc.c:104
void(* h264_idct_dc_add)(uint8_t *dst, int16_t *block, int stride)
Definition: h264dsp.h:85
void ff_h264_idct_add16_neon(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[6 *8])
void ff_weight_h264_pixels_8_neon(uint8_t *dst, int stride, int height, int log2_den, int weight, int offset)
void(* h264_idct_add8)(uint8_t **dst, const int *blockoffset, int16_t *block, int stride, const uint8_t nnzc[15 *8])
Definition: h264dsp.h:96
void(* h264_v_loop_filter_chroma)(uint8_t *pix, ptrdiff_t stride, int alpha, int beta, int8_t *tc0)
Definition: h264dsp.h:61